基于深度LSTM神经网络的大气可降水量估算模型  

Estimation model of precipitable water vapor based on deep LSTM neural network

作　　者：罗宇[1] 罗林艳 范嘉智 段思汝 高文娟 LUO Yu;LUO Lin-yan;FAN Jia-zhi;DUAN Si-ru;GAO Wen-juan(China Meteorological Training Center Hunan Branch,Changsha 410125,China;Hunan Provincial Meteorological Information Center,Changsha 410118,China)

机构地区：[1]中国气象局气象干部培训学院湖南分院,长沙410125 [2]湖南省气象信息中心,长沙410118

出　　处：《湖北农业科学》2020年第2期161-165,共5页Hubei Agricultural Sciences

基　　金：湖南省气象局面上科研项目(XQKJ19B053)。

摘　　要：基于深度长短期记忆(LSTM)神经网络,分别利用地面气象多要素(气温、气压、露点温度、相对湿度、水汽压、小时降水量)和单要素(水汽压)建立怀化地区GPS大气可降水量估算模型LSTM5和LSTM1,并对模型精度进行分析。结果表明,利用地面气象要素建立的2种大气可降水量深度LSTM模型有较好的估算精度,决定系数均大于0.94,均方根误差均值小于1.1581 mm,平均绝对误差均值小于0.7099 mm,平均绝对百分比误差均值小于4.54%,较基于水汽压的可降水量线性拟合或二次多项式拟合模型的估算精度提升了70%以上,且LSTM1模型精度略优于LSTM5模型;模型估算精度与大气可降水量条件相关,当可降水量较低或较高时,模型估算结果更为理想;同时模型估算精度与观测站海拔呈现正相关,观测站海拔越高LSTM模型精度越高。Based on deep long short term memory(LSTM)neural network,the estimation models(LSTM5 and LSTM1)of precipitable water vapor(PWV)in Huaihua distinct are proposed by using multi(air temperature,air pressure,dew point temperature,relative humidity,water vapor pressure and hourly precipitation)and single factor(water vapor pressure)separately,besides the estimation precision of the models are analyzed.As the result shown,the LSTM models have high estimation precision,whose coefficients of determination are both greater than 0.94,mean values of root square error,mean absolute error and mean absolute percentage error are below 1.1581 mm,0.7099 mm and 4.54%respectively.The precision of LSTM models improves more than 70%compared to linear estimation model or quadratic polynomial estimation based on water vapor pressure,and the precision of LSTM1 model slightly better than that of LSTM5.The distribution of estimation errors relates to PWV value,which is first increased and then decreased along with the increasing of PWV.Furthermore,there is negative correlation between the estimation precision of the models and altitude of the stations.

关 键 词：LSTM GPS/MET 大气可降水量 估算模型 怀化地区 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]